blender_execute_code · ClaudeKit Blender MCP: Risk & Policy

WHAT IT DOES

What blender_execute_code does on ClaudeKit Blender MCP

AI agents invoke blender_execute_code to trigger actions in ClaudeKit Blender MCP. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.

WHY IT NEEDS A POLICY

Why blender_execute_code needs a policy

Arbitrary Python code execution is the highest-risk operation category short of financial transactions. An AI agent could use this to: execute malicious code, access system resources, modify arbitrary files, exfiltrate data, or cause uncontrolled effects in Blender or the host system. The blast radius is system-wide.

From the tool's definition Tool description explicitly states 'Execute Python code using Blender' — this permits arbitrary code execution within the Blender environment without documented restrictions on what scripts can run.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

blender_execute_code Rate-limited

blender_execute_code stays usable, but rate-capped — a runaway agent can't fire it dozens of times a minute. Everything else on the server is denied unless you say otherwise.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "blender_execute_code": {
      "limits": [
        {
          "counter": "blender_execute_code_rate",
          "window": "minute",
          "max": 10,
          "scope": "grant"
        }
      ]
    }
  }
}

RATE-LIMIT THIS TOOL →

Instant setup, no code required.

PolicyLayer is an MCP gateway: every tool call is checked against your rule before it reaches ClaudeKit Blender MCP, so you can run agents against it safely.

FAQ

Questions about blender_execute_code

What does the blender_execute_code tool do? +

Execute Python code using Blender. It is categorised as a Execute tool in the ClaudeKit Blender MCP MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on blender_execute_code? +

Register the ClaudeKit Blender MCP server in PolicyLayer and add a rule for blender_execute_code: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches ClaudeKit Blender MCP. Nothing to install.

What risk level is blender_execute_code? +

blender_execute_code is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.

Can I rate-limit blender_execute_code? +

Yes. Add a rate_limit block to the blender_execute_code rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.

How do I block blender_execute_code completely? +

Set action: deny in the PolicyLayer policy for blender_execute_code. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.

What MCP server provides blender_execute_code? +

blender_execute_code is provided by the ClaudeKit Blender MCP server (olbboy/claudekit-blender-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.